Semi-supervised multiple feature analysis for action recognition

Wang, Sen, Ma, Zhigang, Yang, Yi, Li, Xue, Pang, Chaoyi and Hauptmann, Alexander G. (2014) Semi-supervised multiple feature analysis for action recognition. IEEE Transactions on Multimedia, 16 2: 289-298. doi:10.1109/TMM.2013.2293060

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Wang, Sen
Ma, Zhigang
Yang, Yi
Li, Xue
Pang, Chaoyi
Hauptmann, Alexander G.
Title Semi-supervised multiple feature analysis for action recognition
Journal name IEEE Transactions on Multimedia   Check publisher's open access policy
ISSN 1520-9210
Publication date 2014-02-16
Year available 2013
Sub-type Article (original research)
DOI 10.1109/TMM.2013.2293060
Open Access Status Not yet assessed
Volume 16
Issue 2
Start page 289
End page 298
Total pages 10
Place of publication Piscataway, NJ, United States
Publisher Institute of Electrical and Electronics Engineers
Language eng
Subject 2208 Electrical and Electronic Engineering
1711 Signal Processing
2214 Media Technology
1706 Computer Science Applications
Formatted abstract
This paper presents a semi-supervised method for categorizing human actions using multiple visual features. The proposed algorithm simultaneously learns multiple features from a small number of labeled videos, and automatically utilizes data distributions between labeled and unlabeled data to boost the recognition performance. Shared structural analysis is applied in our approach to discover a common subspace shared by each type of feature. In the subspace, the proposed algorithm is able to characterize more discriminative information of each feature type. Additionally, data distribution information of each type of feature has been preserved. The aforementioned attributes make our algorithm robust for action recognition, especially when only limited labeled training samples are provided. Extensive experiments have been conducted on both the choreographed and the realistic video datasets, including KTH, Youtube action and UCF50. Experimental results show that our method outperforms several state-of-the-art algorithms. Most notably, much better performances have been achieved when there are only a few labeled training samples.
Keyword Human action recognition
Multiple feature learning
Semi-supervised learning
Shared structural analysis
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ
Additional Notes Date of Publication : 26 November 2013

Document type: Journal Article
Sub-type: Article (original research)
Collections: Official 2014 Collection
School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 18 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 24 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Sun, 02 Mar 2014, 10:04:29 EST by System User on behalf of School of Information Technol and Elec Engineering